Python 2.7获取网站源代码的几种方式

Posted 2020-08-09

 1 #coding:utf-8
 2 import urllib2,cookielib
 3 
 4 if __name__ == ‘__main__‘:
 5     root_url=‘https://www.baidu.com/‘
 6     # 第一种
 7     print "第一种"
 8     response1=urllib2.urlopen(root_url)
 9     print response1.getcode()
10     print len(response1.read())
11 
12     #第二种
13     print "第二种"
14     request=urllib2.Request(root_url)
15     response2=urllib2.urlopen(request)
16     print response2.getcode()
17     print len(response2.read())
18 
19     # 第三种
20     print "第三种"
21     cj=cookielib.CookieJar()
22     opener=urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
23     urllib2.install_opener(opener)
24     response3 = urllib2.urlopen(root_url)
25     print cj,response3.getcode(),response3.read()